almet/dangerzone
1
0
Fork 0
mirror of https://github.com/freedomofpress/dangerzone.git synced 2025-04-29 18:22:37 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 11

Replace pdfinfo logic (get # pages) with PyMuPDF

Browse source
This commit is contained in:
deeplow 2023-11-16 08:42:38 +00:00
parent 327ab8791f
commit 317deadbe4
No known key found for this signature in database
GPG key ID: 577982871529A52A
1 changed files with 10 additions and 25 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

35
dangerzone/conversion/doc_to_pixels.py
View file

@ -245,33 +245,16 @@ class DocumentToPixels(DangerzoneConverter):
self.percentage += 3 self.percentage += 3
# Obtain number of pages # Obtain number of pages
self.update_progress("Calculating number of pages") doc = fitz.open(pdf_filename)
stdout, _ = await self.run_command( if doc.page_count > errors.MAX_PAGES:
["pdfinfo", pdf_filename],
error_message="PDF file is corrupted",
timeout_message=(
f"Extracting metadata from PDF timed out after {timeout} second"
),
timeout=timeout,
)
search = re.search(r"^Pages:\s*(\d+)\s*\n", stdout.decode(), re.MULTILINE)
if search is not None:
num_pages: int = int(search.group(1))
else:
raise errors.NoPageCountException()
if num_pages > errors.MAX_PAGES:
raise errors.MaxPagesException() raise errors.MaxPagesException()
await self.write_page_count(doc.page_count)
await self.write_page_count(num_pages)
# Get a more precise timeout, based on the number of pages # Get a more precise timeout, based on the number of pages
timeout = self.calculate_timeout(size, num_pages) timeout = self.calculate_timeout(size, doc.page_count)
percentage_per_page = 45.0 / num_pages percentage_per_page = 45.0 / doc.page_count
page_base = "/tmp/page" page_base = "/tmp/page"
doc = fitz.open(pdf_filename) for page in doc.pages():
for page in doc:
# TODO check if page.number is doc-controlled # TODO check if page.number is doc-controlled
page_num = page.number + 1 # pages start in 1 page_num = page.number + 1 # pages start in 1
rgb_filename = f"{page_base}-{page_num}.rgb" rgb_filename = f"{page_base}-{page_num}.rgb"
@ -279,7 +262,9 @@ class DocumentToPixels(DangerzoneConverter):
height_filename = f"{page_base}-{page_num}.height" height_filename = f"{page_base}-{page_num}.height"
self.percentage += percentage_per_page self.percentage += percentage_per_page
self.update_progress(f"Converting page {page_num}/{num_pages} to pixels") self.update_progress(
f"Converting page {page_num}/{doc.page_count} to pixels"
)
pix = page.get_pixmap(dpi=150) pix = page.get_pixmap(dpi=150)
rgb_buf = pix.samples_mv rgb_buf = pix.samples_mv
await self.write_page_width(pix.width, width_filename) await self.write_page_width(pix.width, width_filename)
@ -293,7 +278,7 @@ class DocumentToPixels(DangerzoneConverter):
) )
# XXX: Sanity check to avoid situations like #560. # XXX: Sanity check to avoid situations like #560.
if not running_on_qubes() and len(final_files) != 3 * num_pages: if not running_on_qubes() and len(final_files) != 3 * doc.page_count:
raise errors.PageCountMismatch() raise errors.PageCountMismatch()
# Move converted files into /tmp/dangerzone # Move converted files into /tmp/dangerzone